feishu-calendar
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a local helper script
./scripts/get_feishu_token.shto manage authentication tokens. This is a standard and expected implementation for handling complex OAuth flows and refreshing access tokens.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Feishu API and user-supplied parameters for event creation, which represents a typical attack surface for indirect prompt injection where external data is processed by the agent.\n - Ingestion points: Calendar event summaries, descriptions, and participant data retrieved from the
open.feishu.cnAPI endpoints.\n - Boundary markers: No explicit delimiters or boundary markers for external data are defined in the instruction set.\n
- Capability inventory: The skill can perform network requests to official Feishu domains, read/write to a local token cache file (
./.feishu_token_cache.json), and execute the included authentication script.\n - Sanitization: No specific sanitization or validation logic for external content is described in the markdown instructions.
Audit Metadata